Augmentum

A library for doing image augmentation

Overview:

Image data augmentation is the process of generating new transformed versions of images from the given image dataset to artificially expand the dataset. Augmentum is a library for doing image data augmentation given some images. The main purpose for this library is to apply many data augmentations and allow this via a simple interface without relying on special libraries like opencv, matplotlib, pillow etc.

Development and Contributions:

For development details and contribution instructions, please refer to the contribution guidelines.

Installation:

First, install Python 3.7 (or later) and numpy, and then install this repo as a Python package.

$ pip install numpy
$ pip install Augmentum

Quick Start Example:

Users can get more images by passing their pre-existing images using image augmentation techniques.

import Augmentum
#replace image by the actual grayscale image values
image =  [[1, 1, 1], [1, 0, 0], [1, 0, 0]]
#or instead upload a .raw image file under '.../Augmentum/Augmentum/data/'and
#call process_image() to get a list of lists representations of your grayscale image however
#you have to specify the number of ROWS and COLS in your image (default value is 512x512)
image = Augmentum.process_image(ROWS=512, COLS=512)
new_images = Augmentum.augment_image(image)